Kaplan - Meier survival curve
Last reviewed 01/2018
Kaplan-Meier survival curves (K-M curves) are used to represent outcomes that are times to an event
- K-M curves represent the proportion of the study population still surviving (or free of disease or some other outcome) at successive times
- curves for the intervention of interest and the comparator are often represented on the same graph and a p-value can be calculated to determine the likelihood that there is nodifference between the two survival curves
- as
the number of subjects in each intervention group decreases over time, the curves
are more precise in the earlier periods (left hand side of the survival curves)
than later periods (right hand side of the survival curves)
- in order to account for this, the relative risk (RR) of the event of interest over the entire study period needs to be weighted for the number of subjects available over time (weighted RR is called the Hazard Ratio)
Reference:
- MeReC Briefing (2005);30:1-7.